{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Series\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from pandas import Series, DataFrame\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"obj = pd. Series([1, 3, 5, -7, 9])"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 1\n",
"1 3\n",
"2 5\n",
"3 -7\n",
"4 9\n",
"dtype: int64"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 1, 3, 5, -7, 9])"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj.values"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RangeIndex(start=0, stop=5, step=1)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj.index\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"obj2 = pd.Series([2,4,6,-8,10], index=['a', 'b', 'c', 'd', 'e'])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"a 2\n",
"b 4\n",
"c 6\n",
"d -8\n",
"e 10\n",
"dtype: int64"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2['a']"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"b 4\n",
"c 6\n",
"d -8\n",
"dtype: int64"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2[['b', 'c', 'd']]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"a 10\n",
"b 20\n",
"c 30\n",
"d -40\n",
"e 50\n",
"dtype: int64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2 * 5\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"a 2\n",
"b 4\n",
"c 6\n",
"e 10\n",
"dtype: int64"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2[obj2 > 0] "
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"d -8\n",
"dtype: int64"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2[obj2 < 0]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"e 10\n",
"dtype: int64"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2[obj2 > 8]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"a 7.389056\n",
"b 54.598150\n",
"c 403.428793\n",
"d 0.000335\n",
"e 22026.465795\n",
"dtype: float64"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.exp(obj2)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"population_dict = {'Nordrhein-Westfalen': 17933000, 'Bayern': 13077000, \n",
" 'Baden-Württemberg': 11070000, 'Niedersachsen': 7982000}"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"obj3 = pd.Series(population_dict)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Nordrhein-Westfalen 17933000\n",
"Bayern 13077000\n",
"Baden-Württemberg 11070000\n",
"Niedersachsen 7982000\n",
"dtype: int64"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj3"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"13077000"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj3['Bayern']"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Bayern 13077000\n",
"Baden-Württemberg 11070000\n",
"Niedersachsen 7982000\n",
"dtype: int64"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj3['Bayern':'Niedersachsen']"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"states = ['Berlin','Bayern', 'Niedersachsen', 'Baden-Württemberg']"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"obj4 = pd.Series(population_dict, index=states)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Berlin NaN\n",
"Bayern 13077000.0\n",
"Niedersachsen 7982000.0\n",
"Baden-Württemberg 11070000.0\n",
"dtype: float64"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj4"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Berlin True\n",
"Bayern False\n",
"Niedersachsen False\n",
"Baden-Württemberg False\n",
"dtype: bool"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.isnull(obj4)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Berlin False\n",
"Bayern True\n",
"Niedersachsen True\n",
"Baden-Württemberg True\n",
"dtype: bool"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.notnull(obj4)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Berlin True\n",
"Bayern False\n",
"Niedersachsen False\n",
"Baden-Württemberg False\n",
"dtype: bool"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj4.isnull()"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Nordrhein-Westfalen 17933000\n",
"Bayern 13077000\n",
"Baden-Württemberg 11070000\n",
"Niedersachsen 7982000\n",
"dtype: int64"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj3\n"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Berlin NaN\n",
"Bayern 13077000.0\n",
"Niedersachsen 7982000.0\n",
"Baden-Württemberg 11070000.0\n",
"dtype: float64"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj4"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Baden-Württemberg 22140000.0\n",
"Bayern 26154000.0\n",
"Berlin NaN\n",
"Niedersachsen 15964000.0\n",
"Nordrhein-Westfalen NaN\n",
"dtype: float64"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj3 + obj4"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"obj4.name = 'population'"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"obj4.index.name = 'state'"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"state\n",
"Berlin NaN\n",
"Bayern 13077000.0\n",
"Niedersachsen 7982000.0\n",
"Baden-Württemberg 11070000.0\n",
"Name: population, dtype: float64"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj4"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### DataFrame"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"areacode_dict = {'Nordrhein-Westfalen': 3, 'Bayern': 8, 'Baden-Württemberg': 7, 'Niedersachsen': 3 }"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"areacode = pd.Series(areacode_dict)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Nordrhein-Westfalen 3\n",
"Bayern 8\n",
"Baden-Württemberg 7\n",
"Niedersachsen 3\n",
"dtype: int64"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"areacode"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"population = obj3"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
"states = pd.DataFrame({'population': population, 'areacode': areacode})"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" population | \n",
" areacode | \n",
"
\n",
" \n",
" \n",
" \n",
" Nordrhein-Westfalen | \n",
" 17933000 | \n",
" 3 | \n",
"
\n",
" \n",
" Bayern | \n",
" 13077000 | \n",
" 8 | \n",
"
\n",
" \n",
" Baden-Württemberg | \n",
" 11070000 | \n",
" 7 | \n",
"
\n",
" \n",
" Niedersachsen | \n",
" 7982000 | \n",
" 3 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" population areacode\n",
"Nordrhein-Westfalen 17933000 3\n",
"Bayern 13077000 8\n",
"Baden-Württemberg 11070000 7\n",
"Niedersachsen 7982000 3"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"states"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Nordrhein-Westfalen', 'Bayern', 'Baden-Württemberg', 'Niedersachsen'], dtype='object')"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"states.index"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['population', 'areacode'], dtype='object')"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"states.columns"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Nordrhein-Westfalen 3\n",
"Bayern 8\n",
"Baden-Württemberg 7\n",
"Niedersachsen 3\n",
"Name: areacode, dtype: int64"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"states['areacode']"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [],
"source": [
"data = [{'x': i, 'y': 4 * i}\n",
" for i in range(4)]\n"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" x | \n",
" y | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 1 | \n",
" 1 | \n",
" 4 | \n",
"
\n",
" \n",
" 2 | \n",
" 2 | \n",
" 8 | \n",
"
\n",
" \n",
" 3 | \n",
" 3 | \n",
" 12 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" x y\n",
"0 0 0\n",
"1 1 4\n",
"2 2 8\n",
"3 3 12"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame(data)\n"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" population | \n",
"
\n",
" \n",
" \n",
" \n",
" Nordrhein-Westfalen | \n",
" 17933000 | \n",
"
\n",
" \n",
" Bayern | \n",
" 13077000 | \n",
"
\n",
" \n",
" Baden-Württemberg | \n",
" 11070000 | \n",
"
\n",
" \n",
" Niedersachsen | \n",
" 7982000 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" population\n",
"Nordrhein-Westfalen 17933000\n",
"Bayern 13077000\n",
"Baden-Württemberg 11070000\n",
"Niedersachsen 7982000"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame(population, columns=['population'])"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" population | \n",
" areacode | \n",
"
\n",
" \n",
" \n",
" \n",
" Nordrhein-Westfalen | \n",
" 17933000 | \n",
" 3 | \n",
"
\n",
" \n",
" Bayern | \n",
" 13077000 | \n",
" 8 | \n",
"
\n",
" \n",
" Baden-Württemberg | \n",
" 11070000 | \n",
" 7 | \n",
"
\n",
" \n",
" Niedersachsen | \n",
" 7982000 | \n",
" 3 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" population areacode\n",
"Nordrhein-Westfalen 17933000 3\n",
"Bayern 13077000 8\n",
"Baden-Württemberg 11070000 7\n",
"Niedersachsen 7982000 3"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame({'population': population, 'areacode': areacode})"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" a | \n",
" b | \n",
"
\n",
" \n",
" \n",
" \n",
" x | \n",
" 0.811815 | \n",
" 0.630333 | \n",
"
\n",
" \n",
" y | \n",
" 0.480516 | \n",
" 0.370507 | \n",
"
\n",
" \n",
" z | \n",
" 0.742164 | \n",
" 0.799571 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" a b\n",
"x 0.811815 0.630333\n",
"y 0.480516 0.370507\n",
"z 0.742164 0.799571"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame(np.random.rand(3, 2), \n",
" columns=['a', 'b'],\n",
" index=['x', 'y', 'z'])"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"A = np.zeros(3, dtype=[('A', 'i8'), ('B', 'f8')])"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([(0, 0.), (0, 0.), (0, 0.)], dtype=[('A', '\n",
"\n",
"\n",
" \n",
" \n",
" | \n",
" A | \n",
" B | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 0 | \n",
" 0.0 | \n",
"
\n",
" \n",
" 1 | \n",
" 0 | \n",
" 0.0 | \n",
"
\n",
" \n",
" 2 | \n",
" 0 | \n",
" 0.0 | \n",
"
\n",
" \n",
"
\n",
""
],
"text/plain": [
" A B\n",
"0 0 0.0\n",
"1 0 0.0\n",
"2 0 0.0"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame(A)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}